Traffic violation evidence obtaining method and device based on vehicle continuous trajectory
Traffic violations are judged through vehicle continuous trajectory tracking technology and obtaining characteristic pictures containing license plates, which solves the problem of difficult to obtain vehicle violations in the existing technology and realizes effective evidence for vehicle violations.
Patent Information
- Application Number
- CN202411349582.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2025-02-07
AI Technical Summary
The prior art is difficult to effectively collect the license plate of a vehicle when a traffic violation occurs, resulting in the inability to accurately identify and record the vehicle's illegal behavior.
By using vehicle continuous trajectory tracking technology, the continuous trajectory of the vehicle is obtained and whether there is any traffic violation based on the trajectory. If present, obtaining a first image is used to indicate an offense and a second image is used to display vehicle features, including a clear license plate.
Effective evidence collection for vehicle traffic violations is achieved, ensuring the reliability and accuracy of the first and second pictures as evidence of illegality.
Smart Images
Figure CN119399711A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to a method and device for collecting evidence of traffic violations based on continuous vehicle trajectories. Background Art
[0002] The "GAT832-2014 Technical Specification for Image Evidence Collection of Road Traffic Safety Violations" clearly specifies the image evidence collection of traffic violations. The images used to prove the traffic violations of vehicles should include the violations of the vehicles and clear license plates. However, in actual applications, at the moment of the violation, the license plates are often not clearly visible due to angles, occlusions, etc., so it is impossible to effectively obtain panoramic feature images, and therefore it is impossible to effectively collect evidence of motor vehicle violations.
[0003] In summary, how to effectively collect evidence of a vehicle's traffic violations is an issue that technical personnel in this field urgently need to solve. Summary of the invention
[0004] In view of this, the present application provides a method and device for collecting evidence of traffic violations based on the continuous trajectory of a vehicle, aiming to effectively collect evidence of traffic violations of a vehicle.
[0005] In a first aspect, the present application provides a method for collecting evidence of traffic violations, comprising:
[0006] Using vehicle continuous trajectory tracking technology to obtain the continuous trajectory of the vehicle;
[0007] Determining whether the vehicle has committed a traffic violation according to the continuous trajectory of the vehicle;
[0008] If yes, then obtain a first picture and a second picture corresponding to the vehicle; the first picture is used to indicate the traffic violation of the vehicle; the second picture is used to indicate the vehicle characteristics of the vehicle;
[0009] The first picture and the second picture are determined as evidence of the traffic violation of the vehicle.
[0010] Optionally, before obtaining the continuous trajectory of the vehicle by using the vehicle continuous trajectory tracking technology, the method includes:
[0011] Modeling the road to obtain a three-dimensional model of the road;
[0012] The camera image feature points and the 3D model feature points are mapped one by one, and the mapping relationship from the camera image coordinates to the 3D coordinates is solved.
[0013] Optionally, the obtaining of the continuous trajectory of the vehicle by using the vehicle continuous trajectory tracking technology includes:
[0014] Using the vehicle-connected detection and tracking technology of a single camera, the trajectory coordinates of the vehicle in the camera screen coordinate system are obtained;
[0015] The trajectory coordinates of the vehicle in the camera image coordinate system are mapped to the three-dimensional modeling of the road to obtain a single-camera three-dimensional continuous trajectory of the vehicle.
[0016] Optionally, the obtaining of the continuous trajectory of the vehicle by using the vehicle continuous trajectory tracking technology includes:
[0017] Acquire a plurality of single-camera three-dimensional continuous trajectories of the vehicles;
[0018] The single-camera three-dimensional continuous trajectories of the multiple vehicles are combined to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
[0019] Optionally, after merging the single-camera three-dimensional continuous trajectories of the plurality of vehicles to obtain a multi-camera three-dimensional continuous trajectory of the vehicle, the method further comprises:
[0020] The multi-camera three-dimensional continuous trajectory of the vehicle is post-processed to obtain a processed multi-camera three-dimensional continuous trajectory of the vehicle; the completeness of the processed multi-camera three-dimensional continuous trajectory of the vehicle is greater than the multi-camera three-dimensional continuous trajectory of the vehicle before post-processing.
[0021] Optionally, merging the single-camera three-dimensional continuous trajectories of the plurality of vehicles to obtain a multi-camera three-dimensional continuous trajectory of the vehicle includes:
[0022] Obtaining a license plate of a vehicle corresponding to the single-camera three-dimensional continuous trajectory;
[0023] The single-camera three-dimensional continuous trajectories corresponding to vehicles with the same license plate are merged to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
[0024] Optionally, merging the single-camera three-dimensional continuous trajectories of the plurality of vehicles to obtain a multi-camera three-dimensional continuous trajectory of the vehicle includes:
[0025] The single-camera three-dimensional continuous trajectories corresponding to vehicles that appear at the same time and at the same place and whose similarity is higher than a similarity threshold are merged to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
[0026] In a second aspect, the present application provides a traffic violation evidence collection device based on a continuous trajectory of a vehicle, comprising:
[0027] A first acquisition module is used to acquire the continuous trajectory of the vehicle using the vehicle continuous trajectory tracking technology;
[0028] A judgment module, used for judging whether the vehicle has committed a traffic violation according to the continuous trajectory of the vehicle;
[0029] A second acquisition module is used to acquire a first picture and a second picture corresponding to the vehicle if yes; the first picture is used to indicate the traffic violation of the vehicle; the second picture is used to indicate the vehicle characteristics of the vehicle;
[0030] A determination module is used to determine the first picture and the second picture as evidence of the traffic violation of the vehicle.
[0031] Optionally, the device further comprises:
[0032] A modeling module, used for modeling the road to obtain a three-dimensional modeling of the road;
[0033] The coordinate mapping relationship establishment module is used to map the camera image feature points and the three-dimensional model feature points one by one, and solve the mapping relationship from the camera image coordinates to the three-dimensional coordinates.
[0034] Optionally, the first acquisition module includes:
[0035] A first acquisition unit, used to acquire the trajectory coordinates of the vehicle in the camera screen coordinate system using a single camera vehicle detection and tracking technology;
[0036] A coordinate mapping unit is used to map the trajectory coordinates of the vehicle in the camera image coordinate system to the 3D modeling of the road to obtain a single-camera three-dimensional continuous trajectory of the vehicle.
[0037] Optionally, the first acquisition module includes:
[0038] A second acquisition unit, used to acquire single-camera three-dimensional continuous trajectories of a plurality of the vehicles;
[0039] The merging unit is used to merge the single-camera three-dimensional continuous trajectories of the multiple vehicles to obtain the multi-camera three-dimensional continuous trajectory of the vehicle.
[0040] Optionally, the first acquisition module includes:
[0041] A post-processing unit is used to post-process the multi-camera three-dimensional continuous trajectory of the vehicle to obtain a processed multi-camera three-dimensional continuous trajectory of the vehicle; the completeness of the processed multi-camera three-dimensional continuous trajectory of the vehicle is greater than the multi-camera three-dimensional continuous trajectory of the vehicle before post-processing.
[0042] Optionally, the merging unit includes:
[0043] An acquisition subunit, used to acquire the license plate of the vehicle corresponding to the single camera three-dimensional continuous trajectory;
[0044] The first merging subunit is used to merge the single-camera three-dimensional continuous trajectories corresponding to vehicles with the same license plate to obtain the multi-camera three-dimensional continuous trajectory of the vehicle.
[0045] Optionally, the merging unit includes:
[0046] The second merging subunit is used to merge the single-camera three-dimensional continuous trajectories corresponding to vehicles that appear at the same time and place and whose similarity is higher than a similarity threshold, to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
[0047] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a method for collecting evidence of traffic violations based on the continuous trajectory of a vehicle as described in any one of the implementation methods in the first aspect of the embodiment of the present application is implemented.
[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes a traffic violation evidence collection method based on a continuous trajectory of a vehicle as described in any one of the implementation methods in the first aspect of the embodiment of the present application.
[0049] The present application provides a method for collecting evidence of traffic violations based on the continuous trajectory of a vehicle. When executing the method, the continuous trajectory of the vehicle is first obtained by using the continuous trajectory tracking technology of the vehicle. Then, based on the continuous trajectory of the vehicle, it is determined whether the vehicle has committed a traffic violation. If so, the first picture and the second picture corresponding to the vehicle are obtained, wherein the first picture is used to indicate the traffic violation of the vehicle, and the second picture is used to indicate the vehicle characteristics of the vehicle. Finally, the first picture and the second picture are determined as evidence of the traffic violation of the vehicle. In this way, the continuous trajectory of the vehicle can be obtained by using the continuous trajectory tracking technology of the vehicle, and it is determined whether the vehicle has committed a violation based on the continuous trajectory. If so, the first picture and the second picture corresponding to the vehicle can be obtained, wherein the first picture is used to indicate the traffic violation of the vehicle, and the second picture is used to indicate the vehicle characteristics of the vehicle, that is, the second picture can show a clear license plate, and the first picture and the second picture can be determined as evidence of the traffic violation of the vehicle. In this way, evidence of traffic violations of the vehicle can be effectively collected. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0051] Figure 1 A flow chart of a method for collecting evidence of traffic violations based on continuous vehicle trajectories provided in an embodiment of the present application;
[0052] Figure 2 A top view of a three-dimensional road model provided in an embodiment of the present application;
[0053] Figure 3 A schematic diagram of the detection of vehicle A by camera a provided in an embodiment of the present application at a first time point;
[0054] Figure 4 A schematic diagram of the detection of vehicle A by camera a at a second time point provided in an embodiment of the present application;
[0055] Figure 5 A schematic diagram of the detection of vehicle A by camera a provided in an embodiment of the present application at a third time point;
[0056] Figure 6 A schematic diagram of the detection of vehicle A by camera a provided in an embodiment of the present application at a fourth time point;
[0057] Figure 7 A schematic diagram of a continuous trajectory of a vehicle A provided in an embodiment of the present application;
[0058] Figure 8 A schematic diagram of the detection of vehicle B by camera b provided in an embodiment of the present application at a fifth time point;
[0059] Fig. 9 A schematic diagram of the detection of vehicle B by camera b provided in an embodiment of the present application at a sixth time point;
[0060] Fig.10 A schematic diagram of the detection of vehicle B by camera b provided in an embodiment of the present application at the tenth time point;
[0061] Fig.11 A schematic diagram of the detection of vehicle B by camera c provided in an embodiment of the present application at the seventh time point;
[0062] Fig.12 A schematic diagram of the detection of vehicle B by camera c provided in an embodiment of the present application at an eighth time point;
[0063] Fig.13A schematic diagram of the detection of vehicle B by camera c provided in an embodiment of the present application at a ninth time point;
[0064] Fig.14 A schematic diagram of a continuous trajectory of vehicle B provided in an embodiment of the present application;
[0065] Fig.15 A schematic diagram of the structure of a traffic violation evidence collection device based on a continuous trajectory of a vehicle provided in an embodiment of the present application;
[0066] Fig.16 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0067] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The present application provides a method and device for collecting evidence of traffic violations based on continuous vehicle trajectories, which are used in the field of image processing technology. The above is only an example and does not limit the application field of the method and device provided by the present application.
[0068] The "GAT832-2014 Technical Specification for Image Evidence Collection of Road Traffic Safety Violations" clearly specifies the image evidence collection of traffic violations. The images used to prove the traffic violations of vehicles should include the violations of the vehicles and clear license plates. However, in actual applications, at the moment of the violation, the license plates are often not clearly visible due to angles, occlusions, etc., so it is impossible to effectively obtain panoramic feature images, and therefore it is impossible to effectively collect evidence of motor vehicle violations.
[0069] After research, the inventor proposed the technical solution of this application. When executing the method, the continuous trajectory of the vehicle is first obtained by using the vehicle continuous trajectory tracking technology. Then, based on the continuous trajectory of the vehicle, it is determined whether the vehicle has committed a traffic violation. If so, the first picture and the second picture corresponding to the vehicle are obtained, wherein the first picture is used to indicate the traffic violation of the vehicle, and the second picture is used to indicate the vehicle characteristics of the vehicle. Finally, the first picture and the second picture are determined as evidence of the traffic violation of the vehicle. In this way, the continuous trajectory of the vehicle can be obtained by using the vehicle continuous trajectory tracking technology, and the continuous trajectory can be used to determine whether the vehicle has committed a violation. If so, the first picture and the second picture corresponding to the vehicle can be obtained, wherein the first picture is used to indicate the traffic violation of the vehicle, and the second picture is used to indicate the vehicle characteristics of the vehicle, that is, the second picture can show a clear license plate, and the first picture and the second picture can be determined as evidence of the traffic violation of the vehicle. In this way, evidence of the traffic violation of the vehicle can be effectively collected.
[0070] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.
[0071] See also Figure 1 , Figure 1 A flow chart of a method for collecting evidence of traffic violations based on continuous vehicle trajectories provided in an embodiment of the present application includes:
[0072] S101: Utilizing vehicle continuous trajectory tracking technology to obtain the continuous trajectory of the vehicle.
[0073] Before executing step S101, it is necessary to first perform 3D modeling on the road to obtain a three-dimensional model of the road, and then map the camera image feature points and the three-dimensional model feature points one by one, and then solve the mapping relationship from the camera image coordinates to the three-dimensional coordinates. 3D modeling refers to the collection of 3D point cloud data, image texture data and other data from the real physical world to digitize the physical world. Through automatic acquisition robots or vehicle-mounted acquisition equipment, multi-dimensional physical space data is collected using a variety of sensor fusion technologies such as lidar, inertial navigation, wheel speed meters, AI cameras, etc., and automatic centimeter-level modeling of complex physical environments is achieved through laser matching, multi-sensor fusion, graph optimization and other technologies. It supports the spatial position recognition and calibration of on-site vehicles, objects, people and other targets, and provides a digital foundation for video analysis and intelligent applications. Figure 2 As shown, Figure 2 A top view of a three-dimensional road model provided in an embodiment of the present application.
[0074] In some implementations, a single-camera vehicle-linked detection and tracking technology is used to obtain the trajectory coordinates of the vehicle in the camera image coordinate system, and then the trajectory coordinates of the vehicle in the camera image coordinate system are mapped to the three-dimensional modeling of the road to obtain a single-camera three-dimensional continuous trajectory of the vehicle. Figure 3 , Figure 4 , Figure 5 , Figure 6 As shown, Figure 3 A schematic diagram of the detection of vehicle A by camera a provided in an embodiment of the present application at a first time point; Figure 4 A schematic diagram of the detection of vehicle A by camera a at a second time point provided in an embodiment of the present application; Figure 5A schematic diagram of the detection of vehicle A by camera a provided in an embodiment of the present application at a third time point; Figure 6 A schematic diagram of the detection of vehicle A at a fourth time point by camera a provided in an embodiment of the present application. The fourth time point is after the third time point, the third time point is after the second time point, and the second time point is after the first time point. The vehicle image detection frame j of camera a for vehicle A is used to calibrate the vehicle. The larger the vehicle image detection frame j is, the closer the vehicle is to camera a. Vehicle trajectory d, vehicle trajectory e, and vehicle trajectory f are the driving trajectories of the vehicle between these time points, that is, the trajectory coordinates of vehicle A in the camera image coordinate system of camera a are obtained, and then mapped to the 3D coordinate system of the 3D modeling of the road to obtain the continuous trajectory of vehicle A, such as Figure 7 As shown, Figure 7 This is a schematic diagram of the continuous trajectory of vehicle A provided in an embodiment of the present application, where the continuous trajectory h is the continuous trajectory of vehicle A.
[0075] In some embodiments, the continuous trajectory of the vehicle is a multi-camera 3D continuous trajectory. The multi-camera 3D continuous trajectory is obtained as follows: first determine multiple single-camera 3D continuous trajectories of the vehicle, and then merge the single-camera 3D continuous trajectories of multiple vehicles to obtain the multi-camera 3D continuous trajectory of the vehicle. Figure 8 , Fig. 9 , Fig.10 , Fig.11 , Fig.12 as well as Fig.13 As shown, Figure 8 A schematic diagram of the detection of vehicle B by camera b provided in an embodiment of the present application at a fifth time point; Fig. 9 A schematic diagram of the detection of vehicle B by camera b provided in an embodiment of the present application at a sixth time point; Fig.10 A schematic diagram of the detection of vehicle B by camera b provided in an embodiment of the present application at the tenth time point; Fig.11 A schematic diagram of the detection of vehicle B by camera c provided in an embodiment of the present application at the seventh time point; Fig.12 A schematic diagram of the detection of vehicle B by camera c provided in an embodiment of the present application at an eighth time point; Fig.13 Schematic diagram of the detection of vehicle B by camera c provided in an embodiment of the present application at the ninth time point. Among them, the tenth time point is after the ninth time point, the ninth time point is after the eighth time point, the eighth time point is after the seventh time point, the seventh time point is after the sixth time point, and the sixth time point is after the fifth time point. Fig.14 As shown, Fig.14A schematic diagram of the continuous trajectory of vehicle B provided in an embodiment of the present application. The vehicle screen detection frame i of vehicle B by camera b is used to calibrate vehicle B. The larger the vehicle screen detection frame i is, the closer the vehicle is to camera b. Vehicle trajectory m and vehicle trajectory n are the driving trajectories of the vehicle between these time points, that is, the trajectory coordinates of vehicle B in the camera screen coordinate system of camera b are obtained, and then mapped to the 3D coordinate system of the 3D modeling of the road to obtain the continuous trajectory q of vehicle B. The vehicle screen detection frame k of vehicle B by camera c is used to calibrate vehicle B. The larger the vehicle screen detection frame k is, the closer the vehicle is to camera c. Vehicle trajectory o and vehicle trajectory p are the driving trajectories of the vehicle between these time points, that is, the trajectory coordinates of vehicle B in the camera screen coordinate system of camera c are obtained, and then mapped to the 3D coordinate system of the 3D modeling of the road to obtain the continuous trajectory r of vehicle B. Finally, the continuous trajectory r and the continuous trajectory q are merged to obtain the multi-camera three-dimensional continuous trajectory of vehicle B.
[0076] In addition, before merging the single-camera 3D continuous trajectories of multiple vehicles, it is necessary to first determine that the vehicles corresponding to the multiple single-camera 3D continuous trajectories are the same vehicle, that is, it is necessary to merge the multiple single-camera 3D continuous trajectories corresponding to the same vehicle into a multi-camera 3D continuous trajectory. Specifically, the license plates of the vehicles corresponding to the multiple single-camera 3D continuous trajectories can be obtained first. If the license plates of the vehicles corresponding to the multiple single-camera 3D continuous trajectories are the same, it can be proved that the multiple single-camera 3D continuous trajectories are the single-camera 3D continuous trajectories of the same vehicle. Alternatively, when the first judgment condition and the second judgment condition are met at the same time, it can be proved that the vehicles corresponding to the multiple single-camera 3D continuous trajectories are the same vehicle, wherein the first judgment condition is that at the same time, one camera detects the vehicle identification frame and the corresponding position on the 3D coordinate, and the other camera also detects the vehicle identification frame and the corresponding 3D coordinate position. The second judgment condition is that the vehicle similarity exceeds the similarity threshold. That is, at the same time, the three-dimensional coordinate positions of the vehicles are close, and the vehicle feature similarity is high. Then, the single-camera 3D continuous trajectories corresponding to the vehicles that appear at the same time and at the same place and whose similarity is higher than the similarity threshold can be merged to obtain the multi-camera 3D continuous trajectory of the vehicle.
[0077] In some implementations, after obtaining the multi-camera three-dimensional continuous trajectory, the continuous trajectory can be post-processed. Trajectory post-processing refers to trajectory completion, merging, and splitting strategies. These strategies are not calculated in real time, but need to be calculated forward and backward in time to make the trajectory more complete and accurate.
[0078] S102: Determine whether the vehicle has committed any traffic violation based on the continuous trajectory of the vehicle.
[0079] Through the continuous trajectory of the vehicle obtained in step S101, it can be determined whether the vehicle has committed a traffic violation. If so, step S103 is executed; if not, step S104 is executed.
[0080] S103: Obtain a first picture and a second picture corresponding to the vehicle.
[0081] When a vehicle commits a traffic violation, a first picture and a second picture are obtained, wherein the first picture can accurately capture the vehicle's violation, and the second picture is a panoramic feature picture, which is a picture containing the full view of the front or rear of the motor vehicle, license plate, color, model, and significant geographical features. In this embodiment of the present application, the second picture must include a clear license plate.
[0082] S104: Continue to obtain the continuous trajectory of the vehicle.
[0083] S105: Determine the first image and the second image as evidence of the vehicle's traffic violation.
[0084] Since the first picture records the illegal behavior of the vehicle, the license plate of the vehicle can be clearly seen in the second picture, and the vehicle in the first picture and the vehicle in the second picture are the same vehicle, the first picture and the second picture can be used as evidence of the traffic violation of the illegal vehicle.
[0085] In the embodiment of the present application, when executing the method, the continuous trajectory of the vehicle is first obtained by using the vehicle continuous trajectory tracking technology. Then, based on the continuous trajectory of the vehicle, it is determined whether the vehicle has committed a traffic violation. If so, the first picture and the second picture corresponding to the vehicle are obtained, wherein the first picture is used to indicate the traffic violation of the vehicle, and the second picture is used to indicate the vehicle characteristics of the vehicle. Finally, the first picture and the second picture are determined as evidence of the traffic violation of the vehicle. In this way, the continuous trajectory of the vehicle can be obtained by using the vehicle continuous trajectory tracking technology, and it is determined whether the vehicle has committed a violation based on the continuous trajectory. If so, the first picture and the second picture corresponding to the vehicle can be obtained, wherein the first picture is used to indicate the traffic violation of the vehicle, and the second picture is used to indicate the vehicle characteristics of the vehicle, that is, the second picture can show a clear license plate, and the first picture and the second picture can be determined as evidence of the traffic violation of the vehicle. In this way, evidence of the traffic violation of the vehicle can be effectively collected.
[0086] The above are some specific implementations of the traffic violation evidence collection method based on the continuous trajectory of the vehicle provided by the embodiment of the present application. Based on this, the present application also provides a corresponding device. The device provided by the embodiment of the present application will be introduced from the perspective of functional modularization.
[0087] like Fig.15 As shown, Fig.15A schematic diagram of a traffic violation evidence collection device based on a continuous vehicle trajectory provided in an embodiment of the present application, the traffic violation evidence collection device based on a continuous vehicle trajectory 1500 comprises:
[0088] A first acquisition module 1510 is used to acquire a continuous trajectory of the vehicle using a vehicle continuous trajectory tracking technology;
[0089] A judgment module 1520, configured to judge whether the vehicle has committed a traffic violation according to the continuous trajectory of the vehicle;
[0090] The second acquisition module 1530 is used to acquire a first picture and a second picture corresponding to the vehicle if yes; the first picture is used to indicate the traffic violation of the vehicle; the second picture is used to indicate the vehicle characteristics of the vehicle;
[0091] The determination module 1540 is used to determine the first picture and the second picture as evidence of the traffic violation of the vehicle.
[0092] Optionally, the device 1500 further includes:
[0093] A modeling module, used for modeling the road to obtain a three-dimensional modeling of the road;
[0094] The coordinate mapping relationship establishment module is used to map the camera image feature points and the three-dimensional model feature points one by one, and solve the mapping relationship from the camera image coordinates to the three-dimensional coordinates.
[0095] Optionally, the first acquisition module 1510 includes:
[0096] A first acquisition unit, used to acquire the trajectory coordinates of the vehicle in the camera screen coordinate system using a single camera vehicle detection and tracking technology;
[0097] A coordinate mapping unit is used to map the trajectory coordinates of the vehicle in the camera image coordinate system to the 3D modeling of the road to obtain a single-camera three-dimensional continuous trajectory of the vehicle.
[0098] Optionally, the first acquisition module 1510 includes:
[0099] A second acquisition unit, used to acquire single-camera three-dimensional continuous trajectories of a plurality of the vehicles;
[0100] The merging unit is used to merge the single-camera three-dimensional continuous trajectories of the multiple vehicles to obtain the multi-camera three-dimensional continuous trajectory of the vehicle.
[0101] Optionally, the first acquisition module 1510 includes:
[0102] A post-processing unit is used to post-process the multi-camera three-dimensional continuous trajectory of the vehicle to obtain a processed multi-camera three-dimensional continuous trajectory of the vehicle; the completeness of the processed multi-camera three-dimensional continuous trajectory of the vehicle is greater than the multi-camera three-dimensional continuous trajectory of the vehicle before post-processing.
[0103] Optionally, the merging unit includes:
[0104] An acquisition subunit, used to acquire the license plate of the vehicle corresponding to the single camera three-dimensional continuous trajectory;
[0105] The first merging subunit is used to merge the single-camera three-dimensional continuous trajectories corresponding to vehicles with the same license plate to obtain the multi-camera three-dimensional continuous trajectory of the vehicle.
[0106] Optionally, the merging unit includes:
[0107] The second merging subunit is used to merge the single-camera three-dimensional continuous trajectories corresponding to vehicles that appear at the same time and place and whose similarity is higher than a similarity threshold, to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
[0108] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.
[0109] like Fig.16 As shown, the computer device 01 is in the form of a general computing device. The components of the computer device 01 may include but are not limited to: one or more processors or processing units 03, a system memory 08, and a bus 04 connecting different system components (including the system memory 08 and the processing unit 03).
[0110] Bus 04 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.
[0111] The computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 01, including volatile and non-volatile media, removable and non-removable media.
[0112] The system memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. The computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 11 may be used to read and write non-removable, non-volatile magnetic media ( Fig.16 not shown, usually called a "hard drive"). Although Fig.16 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 04 via one or more data medium interfaces. The memory 08 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.
[0113] A program / utility 12 having a set (at least one) of program modules 13 may be stored, for example, in the memory 08, such program modules 13 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 13 generally perform the functions and / or methods of the embodiments described herein.
[0114] The computer device 01 may also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), one or more devices that enable a user to interact with the computer device 01, and / or any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via input / output (I / O) interface 06. Furthermore, the computer device 01 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via network adapter 05. Fig.16 As shown, the network adapter 05 communicates with other modules of the computer device 01 via the bus 04. It should be understood that although Fig.16 Not shown, other hardware and / or software modules may be used in conjunction with computer device 01, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0115] The processor unit 03 executes various functional applications and data processing by running programs stored in the system memory 08, such as implementing a traffic violation evidence collection method based on a continuous trajectory of a vehicle provided in an embodiment of the present application.
[0116] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0117] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.
[0118] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.
[0119] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.
Claims
1. A traffic violation evidence collection method based on vehicle continuous trajectory, characterized in that: include: Using vehicle continuous trajectory tracking technology to obtain the continuous trajectory of the vehicle; Determining whether the vehicle has committed a traffic violation according to the continuous trajectory of the vehicle; If yes, then obtain a first picture and a second picture corresponding to the vehicle; the first picture is used to indicate the traffic violation of the vehicle; the second picture is used to indicate the vehicle characteristics of the vehicle; The first picture and the second picture are determined as evidence of the traffic violation of the vehicle.
2. The method according to claim 1, characterized in that Before obtaining the continuous trajectory of the vehicle by using the vehicle continuous trajectory tracking technology, the method includes: Modeling the road to obtain a three-dimensional model of the road; The camera image feature points and the 3D model feature points are mapped one by one, and the mapping relationship from the camera image coordinates to the 3D coordinates is solved.
3. The method according to claim 2, characterized in that The method of using the vehicle continuous trajectory tracking technology to obtain the continuous trajectory of the vehicle includes: Using a single-camera vehicle detection and tracking technology, the trajectory coordinates of the vehicle in the camera screen coordinate system are obtained; The trajectory coordinates of the vehicle in the camera image coordinate system are mapped to the three-dimensional modeling of the road to obtain a single-camera three-dimensional continuous trajectory of the vehicle.
4. The method according to claim 3, characterized in that The method of using the vehicle continuous trajectory tracking technology to obtain the continuous trajectory of the vehicle includes: Acquire a plurality of single-camera three-dimensional continuous trajectories of the vehicles; The single-camera three-dimensional continuous trajectories of the multiple vehicles are combined to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
5. The method according to claim 4, characterized in that After merging the single-camera three-dimensional continuous trajectories of the plurality of vehicles to obtain the multi-camera three-dimensional continuous trajectory of the vehicle, the method further includes: The multi-camera three-dimensional continuous trajectory of the vehicle is post-processed to obtain a processed multi-camera three-dimensional continuous trajectory of the vehicle; the processed multi-camera three-dimensional continuous trajectory of the vehicle has a greater degree of completeness than the multi-camera three-dimensional continuous trajectory of the vehicle before post-processing.
6. The method according to claim 4, characterized in that The step of merging the single-camera three-dimensional continuous trajectories of the plurality of vehicles to obtain a multi-camera three-dimensional continuous trajectory of the vehicle includes: Obtaining a license plate of a vehicle corresponding to the single-camera three-dimensional continuous trajectory; The single-camera three-dimensional continuous trajectories corresponding to vehicles with the same license plate are merged to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
7. The method according to claim 4, characterized in that The step of merging the single-camera three-dimensional continuous trajectories of the plurality of vehicles to obtain a multi-camera three-dimensional continuous trajectory of the vehicle includes: The single-camera three-dimensional continuous trajectories corresponding to vehicles that appear at the same time and at the same place and whose similarity is higher than a similarity threshold are merged to obtain a multi-camera three-dimensional continuous trajectory of the vehicle.
8. A traffic violation evidence collection device based on continuous vehicle trajectory, characterized in that: include: A first acquisition module is used to acquire the continuous trajectory of the vehicle using the vehicle continuous trajectory tracking technology; A judgment module, used for judging whether the vehicle has committed a traffic violation according to the continuous trajectory of the vehicle; A second acquisition module is used to acquire a first picture and a second picture corresponding to the vehicle if yes; the first picture is used to indicate a traffic violation of the vehicle; The second picture is used to indicate vehicle features of the vehicle; A determination module is used to determine the first picture and the second picture as evidence of the traffic violation of the vehicle.
9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for collecting evidence of traffic violations based on the continuous trajectory of a vehicle as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the method for collecting traffic violation evidence based on a continuous trajectory of a vehicle as described in any one of claims 1 to 7.